Task-Efficient Agent Evaluation Using Cached Traces
cs.AI
Submitted: 2026-11-04
Updated: 2026-11-04
Terminology
Sources
- Consistent estimation of generative model representations in the data kernel perspective space
- Crafting Interpretable Embeddings by Asking LLMs Questions
- Efficient Benchmarking Is Just Feature Selection and Multiple Regression
- Detecting Perspective Shifts in Multi-agent Systems
- Why Do Multi-Agent LLM Systems Fail?
- DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence
- Comparing Foundation Models using Data Kernels
- Statistical inference on black-box generative models in the data kernel perspective space
- Benchmark Prediction with Sparse and Unpaired Cached Responses
- Query-efficient model evaluation using cached responses
- Control Charts for Multi-agent Systems
- SWE-bench: Can Language Models Resolve Real-World GitHub Issues?
- Holistic Agent Leaderboard: The Missing Infrastructure for AI Agent Evaluation
- metabench -- A Sparse Benchmark of Reasoning and Knowledge in Large Language Models
- Towards General Text Embeddings with Multi-stage Contrastive Learning
- tinyBenchmarks: evaluating LLMs with fewer examples
- Beyond Resolution Rates: Behavioral Drivers of Coding Agent Success and Failure
- Terminal-Bench: Benchmarking Agents on Hard, Realistic Tasks in Command Line Interfaces
- Text and Code Embeddings by Contrastive Pre-Training
- Training Sparse Mixture Of Experts Text Embedding Models
Related papers
- Multi-Objective Structured Pruning of LLMs for Latency and Model Size Optimization
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Embeddings for Preferences, Not Semantics
- Can We Trust Item Response Theory for AI Evaluation?
- Diagnosing Task Insensitivity in Language Agents